AN INVESTIGATION INTO THE USE OF PHYSICAL MODELING FOR THE PREDICTIONOF VARIOUS FEATURE TYPES VISIBLE FROM DIFFERENT VIEWPOINTS

Given that aspect graph and viewsphere-based object recognition system s provide a valid mechanism for 3D object recognition of man-made obje cts, this paper provides a flexible, automated, and general purpose te chnique for generating the view information for each viewpoint. An adv antage of the work is that the technique is unaffected by object shape . The only limitation is that the object can be described by a boundar y representation. A second advantage is that the technique can include other feature types such as specularity. The reason for this is that raytracing techniques are used to simulate the physical process of ima ge generation. Hence it is extendible to visible features resulting fr om effects due to lighting, surface texture, color, transparency, etc. The work described in this paper shows how occluding and nonoccluding edge-based features can be extracted using image processing technique s and then parametrized and also how regions of specularity can be pre dicted and described. The use of physical modeling enables situations to be simulated and predicted that are intractable for CAD-based metho ds (e.g., multiscale feature prediction). An advantage of the method i s that the interface between the technique and the raytracing module i s a rendered image. Should better physics-based image formation algori thms become available, then they could replace the raytracing module w ith little modification to the rest of the method. (C) 1995 Academic P ress, Inc.